CN104573675A - Operating image displaying method and device - Google Patents
Operating image displaying method and device Download PDFInfo
- Publication number
- CN104573675A CN104573675A CN201510047554.1A CN201510047554A CN104573675A CN 104573675 A CN104573675 A CN 104573675A CN 201510047554 A CN201510047554 A CN 201510047554A CN 104573675 A CN104573675 A CN 104573675A
- Authority
- CN
- China
- Prior art keywords
- ordinate
- image
- target area
- flow diagram
- diagram picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an operating image displaying method and device. The method includes: acquiring an operating image; determining a target area in the operating image; marking the target area in the operating image. The operating image displaying method and device has the advantage that operating cost can be reduced for users.
Description
Technical field
The present invention relates to technical field of data processing, particularly relate to a kind of methods of exhibiting and device of flow diagram picture.
Background technology
Mobile applications is the application program run on the mobile apparatus, and user can by running mobile applications by mobile network's obtaining information.The function of mobile applications gets more and more, and a kind of mobile applications can answer an operation difficult problem for User, facilitates User to use, such as, and the operation side that Baidu proposes.User, when using this kind of application program, first can take pictures to operation, obtain flow diagram picture, then search for according to flow diagram picture, obtain answer.
In prior art, after obtaining flow diagram picture, can on flow diagram picture display system acquiescence crop box, user can operate this crop box, selects the content that will search for, after selection by submit to search select content.
But this mode needs user to select by hand, there is certain cost and cost.
Summary of the invention
The present invention is intended to solve one of technical matters in correlation technique at least to a certain extent.
For this reason, one object of the present invention is the methods of exhibiting proposing a kind of flow diagram picture, and the method can reduce cost and the cost of user operation.
Another object of the present invention is the exhibiting device proposing a kind of flow diagram picture.
For achieving the above object, the methods of exhibiting of the flow diagram picture that first aspect present invention embodiment proposes, comprising: obtain flow diagram picture; Determine the target area in described flow diagram picture; In described flow diagram picture, identify described target area.
The methods of exhibiting of the flow diagram picture that first aspect present invention embodiment proposes, by determining the target area in flow diagram picture, and target area is identified in flow diagram picture, directly can orient target area, the automatic identification in realize target region, do not need the manual select target region of user, thus reduce cost and the cost of user operation.
For achieving the above object, the exhibiting device of the flow diagram picture that second aspect present invention embodiment proposes, comprising: acquisition module, for obtaining flow diagram picture; Determination module, for determining the target area in described flow diagram picture; Identification module, in described flow diagram picture, identifies described target area.
The exhibiting device of the flow diagram picture that second aspect present invention embodiment proposes, by determining the target area in flow diagram picture, and target area is identified in flow diagram picture, directly can orient target area, the automatic identification in realize target region, do not need the manual select target region of user, thus reduce cost and the cost of user operation.
The aspect that the present invention adds and advantage will part provide in the following description, and part will become obvious from the following description, or be recognized by practice of the present invention.
Accompanying drawing explanation
The present invention above-mentioned and/or additional aspect and advantage will become obvious and easy understand from the following description of the accompanying drawings of embodiments, wherein:
Fig. 1 is the schematic flow sheet of the methods of exhibiting of the flow diagram picture that one embodiment of the invention proposes;
Fig. 2 is the schematic flow sheet determining operation objective area in image in the embodiment of the present invention;
Fig. 3 is the effect schematic diagram identifying target area in the embodiment of the present invention in flow diagram picture;
Fig. 4 is the schematic flow sheet of the methods of exhibiting of the flow diagram picture that another embodiment of the present invention proposes;
Fig. 5 is the structural representation of the exhibiting device of the flow diagram picture that another embodiment of the present invention proposes;
Fig. 6 is the structural representation of the exhibiting device of the flow diagram picture that another embodiment of the present invention proposes.
Embodiment
Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has element that is identical or similar functions from start to finish.Being exemplary below by the embodiment be described with reference to the drawings, only for explaining the present invention, and can not limitation of the present invention being interpreted as.On the contrary, embodiments of the invention comprise fall into attached claims spirit and intension within the scope of all changes, amendment and equivalent.
Fig. 1 is the schematic flow sheet of the methods of exhibiting of the flow diagram picture that one embodiment of the invention proposes, and the method comprises:
S11: obtain flow diagram picture.
Such as, user can take pictures to the operation that will search for, and obtains flow diagram picture, or user also directly can select flow diagram picture from existing picture library.
After user takes pictures or selects to obtain flow diagram picture, mobile applications can receive user and takes pictures or select the flow diagram picture that obtains.
S12: determine the target area in described flow diagram picture.
Wherein, target area is the region at the content place that user will search for, such as, and the region at exercise question place in flow diagram picture.
Target area can be one or more, multiplely refers at least two.
Optionally, see Fig. 2, the described target area determined in described flow diagram picture, comprising:
S21: extract the character features information in described flow diagram picture, obtains the image removing non-legible information.
The mode extracting character features information can have multiple, such as, directly can carry out content recognition to original flow diagram picture, thus extract character features information, and character features information is retained in flow diagram picture, remove non-legible information, thus obtain the image removing non-legible information.Concrete, when extracting character features information, first can carry out connected domain division to original flow diagram picture, connected domain divides when such as the number of continuous image vegetarian refreshments identical for pixel value being greater than a threshold value and obtains a connected domain, after connected domain divides, content in each connected domain is identified, connected domain is distinguished character area and non-legible region, character area such as comprises word, letter, one in numeral or multinomial, concrete, can according to picture element density, region picture element density being greater than threshold value is defined as character area.Or,
Character features information in the described flow diagram picture of described extraction, obtains the image removing non-legible information, comprising:
Gray processing is carried out to described flow diagram picture, obtains gray level image;
Described gray level image is sampled, obtains the image after sampling;
By the Nonlinear magnify after described sampling to described flow diagram as formed objects, the image after being amplified;
Calculate the error image of the image after described flow diagram picture and described amplification;
Binary conversion treatment is carried out to described error image, obtains the image after binary conversion treatment;
Remove the connected domain in non-legible region in the image after described binary conversion treatment, obtain the image of the non-legible information of described removal.
The particular content of the mode of this extraction character features information can see subsequent embodiment.
S22: horizontal direction projection is carried out to the image of the non-legible information of described removal, obtains the ordinate pair of target area.
Optionally, the described image to the non-legible information of described removal carries out horizontal direction projection, obtains the ordinate pair of target area, comprising:
Obtain h1 and h2, and form ordinate pair by h1 and h2, wherein, as h1≤hi≤h2, the horizontal direction projection value that hi is corresponding is greater than the first projection threshold value, and h1<h2, h1 and h2 represent two ordinates respectively.
First projection threshold value can be determined according to pixel average, such as, the coefficient * pixel average of the first projection threshold value=default, the expression formula of pixel average can specifically: the high h of row removing the sum of non-zero pixel number in the image of non-legible information/the remove image of non-legible information.
Such as, suppose that ordinate is from 0, first can judge whether the horizontal projection value that hi=0 is corresponding is greater than the first projection threshold value, if be greater than, then continue to judge whether the horizontal projection value that hi=1 is corresponding is greater than the first projection threshold value, if be greater than the judgement continuing next adjacent ordinate, suppose that the horizontal projection value up to hi=5 is corresponding is all greater than the first projection threshold value, and horizontal projection value corresponding to hi=6 is less than the first projection threshold value, then one group of ordinate is to being expressed as <0,5>; Afterwards, determined level projection value from hi=7 can be continued and whether be greater than the first projection value.Wherein, the horizontal projection value that hi is corresponding refers to that in the image of the non-legible information of described removal, ordinate is that in the one-row pixels point of hi instruction, pixel value is the number of non-zero pixel.
Be understandable that, ordinate is to being many groups, and many group ordinates can form ordinate queue, and such as, ordinate is to comprising: <0,5>, <7,10> etc.
Further, adopt the ordinate determined of aforesaid way to being many groups, such as, <0,5>, <7,10> etc., afterwards can to many group ordinates to merging and/or Transformatin.
The described ordinate to described at least two groups, to carrying out Transformatin, comprising:
Corresponding current ordinate pair to be processed, calculates the difference of current ordinate centering two ordinates;
If described difference is less than the first distance difference, then remove described current ordinate pair.
Such as, to can often organize ordinate to being defined as current ordinate pair successively, suppose that current ordinate is to being <0,5>, then can calculate 5-0, if difference 5-0=5 is less than the first distance difference, then remove this ordinate to <0,5>, otherwise retain, the first distance difference can be default.
Optionally, the described ordinate to described at least two groups, to carrying out merging treatment, comprising:
Corresponding first group of adjacent ordinate to be processed to second group of ordinate pair, calculate described first group of ordinate pair spacing value right with described second group of ordinate;
If described spacing value is less than second distance difference, then merge described first group of ordinate to second group of ordinate pair.
Such as, can successively by two groups of adjacent ordinates to be defined as first group of ordinate to second group of ordinate pair, suppose first group of ordinate to second group of ordinate to being <0 respectively, 5> and <7, 10>, the right spacing value of two groups of ordinates refers to the difference of next group ordinate to medium and small coordinate figure and the large coordinate figure of upper one group of ordinate centering, such as, the right spacing value of above-mentioned two groups of ordinates is 7-5=2, if spacing value 2 is less than second distance difference, then merge these two groups of ordinates to <0, 5> and <7, 10>, otherwise nonjoinder, second distance difference can be determined by the coordinate figure right according to two groups of ordinates, such as, suppose that two groups of ordinates are to being <h1 respectively, h2> and <h3, h4>, then second distance difference can be expressed as: (h3-h2)/((h2-h1+h4-h3)/2).
S23: carry out vertical direction projection to the image of the non-legible information of described removal, corresponding described ordinate is to obtaining horizontal ordinate pair.
Optionally, the described image to the non-legible information of described removal carries out vertical direction projection, and corresponding described ordinate, to obtaining horizontal ordinate pair, comprising:
Obtain w1 and w2, and form horizontal ordinate pair by w1 and w2, wherein, w1<w2, w1 is the abscissa value that the vertical direction projection value of first correspondence from the leftmost side of the image of the non-legible information of described removal is greater than the second projection threshold value, and w2 is the abscissa value that the vertical direction projection value of first correspondence from the rightmost side of the image of the non-legible information of described removal is greater than the second projection threshold value.Second projection value can pre-set.
Such as, suppose that horizontal ordinate is from 0, first can judge whether the vertical projection value that wj=0 is corresponding is greater than the second projection threshold value, if be less than, then continue to judge whether the vertical projection value that wj=1 is corresponding is less than the second projection threshold value, if be less than the judgement continuing next adjacent horizontal ordinate, suppose that the horizontal projection value up to wj=5 is corresponding is all less than the second projection threshold value, and vertical projection value corresponding to wj=6 is greater than the second projection threshold value, then w1=6, on the other hand, first judge whether the vertical projection value that wj=w-1 (w is total number of the pixels across point of flow diagram picture) is corresponding is greater than the second projection threshold value, if be less than, then continue to judge whether the vertical projection value that wj=w-2 is corresponding is less than the second projection threshold value, if be less than the judgement continuing next adjacent horizontal ordinate, suppose that the horizontal projection value up to wj=w-8 is corresponding is all less than the second projection threshold value, and vertical projection value corresponding to wj=w-9 is greater than the second projection threshold value, then w2=w-9, therefore, one group of horizontal ordinate is to being expressed as <6, w-9>.Wherein, correspondence often organizes ordinate pair, and the vertical projection value that wj is corresponding refers to that this group ordinate is in the region at place, and in a row pixel of wj instruction, pixel value is the number of non-zero pixel.
Be understandable that, if ordinate is to being many groups, and to many group ordinates to when having carried out removal and/or merging treatment, horizontal ordinate to be corresponding remove and/or ordinate after merging treatment to obtaining.
S24: according to described ordinate to described horizontal ordinate pair, obtain the target area in described flow diagram picture.
Such as, corresponding <h1, the horizontal ordinate of h2> is to being <w1, w2>, then target area is <h1, h2, w1, w2>, specifically to refer to as in industry image ordinate from h1 to h2, and the region of the pixel composition of horizontal ordinate from w1 to w2.
S13: in described flow diagram picture, identify described target area.
Concrete, in described flow diagram picture, the border of described target area can be shown with crop box form.
Optionally, after on border crop box being arranged on target area, user can also operate crop box further, such as, and the position of mobile crop box, and/or, change the size etc. of crop box.
When target area is multiple, after determining all target areas, all target areas can be identified in flow diagram picture; Or, optimum target region can be determined from all target areas, in flow diagram picture, identify optimum target region; Or, also can identify all target areas, also identify optimum target region, and all target areas and optimum target region identify in different ways.
Such as, see Fig. 3, on flow diagram picture, can identify all target areas with the first crop box 31, identifying optimum target region with the second crop box 32 is example, and wherein, the first crop box is such as white, and the second crop box is such as blue.
Optionally, describedly in all target areas, determine optimum target region, comprising:
According at least one item in the following item in described target area, in all target areas, determine optimum target region: the content body in target area, the height of target area, the position of target area.Concrete, content body, highly, the specific requirement that position meets can pre-set.
Further, after determining target area, can obtain and show the result for retrieval corresponding with each target area.Concrete, service end can be issued in target area by client, carry out image recognition and the result for retrieval that the acquisition such as retrieval is corresponding with each target area in a database, and result for retrieval is sent to client to show by service end by service end.
After the result for retrieval of multiple target areas that client obtains, the form of different result for retrieval according to page turning can be shown, wherein, the result for retrieval in different target region can the exercise question order corresponding according to target area sort, or, sort according to priority, priority can according to the height of target area, and the information such as position are determined.
In the present embodiment, by determining the target area in flow diagram picture, and identify target area in flow diagram picture, directly can orient target area, the automatic identification in realize target region, does not need the manual select target region of user, thus reduces cost and the cost of user operation.
Fig. 4 is the schematic flow sheet of the methods of exhibiting of the flow diagram picture that another embodiment of the present invention proposes, and the method comprises:
S401: obtain the first image.
First image is original flow diagram picture, can be taken pictures obtain by user to operation exercise question.
S402: gray processing is carried out to the first image, obtains gray level image.
Such as, the first image is RGB image normally, RGB image can be carried out gray processing, obtain gray level image, to reduce operand.
S403: sample to gray level image, obtains the second image.
Second image is the image after sampling.
Concrete, can sample to gray level image according to preset ratio, such as, extract a pixel at horizontal and vertical every N number of pixel of gray level image.Wherein, horizontal and vertically also can be called horizontal direction and vertical direction, horizontal and vertical extraction ratio can be identical.
Suppose that the size of the first image is w*h, then the size of gray level image is also w*h, and the size of the second image is i*j, wherein, w and i is the number of pixels across point, h and j is the number of longitudinal pixel, and, w>i, h>j, and, w/i=h/j.
S404: amplify the second image, obtains the 3rd image, and the size of the 3rd image is identical with the size of the first image.
Such as, bilinear interpolation mode can be adopted to amplify the second image, obtain the 3rd image, the size of the 3rd image is w*h.
S405: difference operation is carried out to the first image and the 3rd image, obtains the 4th image.
Such as, because the first image is identical with the size of the 3rd image, then can pixel on corresponding each position, calculate the first pixel value and the second pixel value obtains difference, first pixel value is the pixel value of the pixel in the first image on this position, second pixel value is the pixel value of the pixel in the second image on this position, and this difference is defined as the pixel value of the pixel in the 4th image on this position.
S406: binaryzation is carried out to the 4th image, and after removing the connected domain in non-legible region, obtain the 5th image.
Wherein, pixel value threshold value can be pre-set, the pixel value being greater than this pixel value threshold value in the 4th image is set to 255, the pixel value being less than this pixel value threshold value is set to 0, thus realize binaryzation in the 4th image.
Non-legible region can be determined according to pixel value, such as, the region of the pixel composition after binaryzation being 255 is defined as non-legible region, connected domain refers to that the number of the continuous image vegetarian refreshments that pixel value is identical is greater than the region of number threshold value, such as, number threshold value can be pre-set, when the number that continuous print pixel value is the pixel of 255 is greater than number threshold value, then this continuous print pixel value is that the region of the pixel composition of 255 can be called the connected domain in non-legible region, and then removes the connected domain in this non-legible region.Concrete, removal can refer to and the pixel value of the pixel in the connected domain in non-legible region is set to 0.
S407: carry out image level projection to the 5th image, determines the ordinate queue of target area.
Wherein, ordinate queue can comprise at least one group of ordinate pair.
Suppose that one group of ordinate is to being expressed as <h1, h2>, the then following condition of demand fulfillment:
As h1≤hi≤h2, the horizontal projection value that hi is corresponding is greater than the first projection threshold value, first projection threshold value can be determined according to pixel average, such as, the coefficient * pixel average of the first projection threshold value=default, the expression formula of pixel average can specifically: the high h of row of sum/the 5th image of non-zero pixel number in the 5th image.
Concrete, suppose that total coordinate is from 0, first can calculate horizontal projection value during hi=0, if this horizontal projection value is greater than the 3rd threshold value, calculate horizontal projection value during hi=1 again, if this horizontal projection value is also greater than the 3rd threshold value, continue to calculate horizontal projection value corresponding to next ordinate, horizontal projection value when supposing hi=5 is greater than the 3rd threshold value, and horizontal projection value during hi=6 is less than the 3rd threshold value, then one group of ordinate is to being expressed as <0,5>.Afterwards, can continue to calculate horizontal projection value from hi=7 and whether be greater than the 3rd threshold value, thus new ordinate pair can be determined.
Through above-mentioned process, target area can be one or more, multiplely refers at least two.Each target area can corresponding one group of ordinate pair, such as, the ordinate of a target area is to being expressed as <h1, h2>, the ordinate of at least one group to ordinate queue can be formed, such as, ordinate queue comprises: <h1, h2>, <h3, h4>.
Be understandable that, with <h1, h2> is example, h1 and h2 refers to ordinate respectively, when ordinate is from 0 open numbering, 0≤h1<h2≤w-1, when ordinate is from 1 open numbering, 1≤h1<h2≤w, h1 and h2 is not limited to be two adjacent ordinates.
Further, the ordinate that employing aforesaid way is determined, afterwards can to many group ordinates to merging and/or Transformatin to being many groups.Concrete, merging and/or Transformatin see a upper embodiment, can not repeat them here.
S408: carry out image vertical projection to the 5th image, determines the horizontal ordinate team of each target area.
When to the ordinate of at least one target area to merge and/or after Transformatin, corresponding horizontal ordinate pair can be determined in the target area after corresponding each process.
Suppose that the horizontal ordinate of a target area represents with <w1, w2>, then w1, w2 meet following condition:
W1 is the horizontal ordinate that first vertical projection value from the leftmost side of the 5th image is greater than the second projection threshold value, and w2 is the horizontal ordinate that first vertical projection value from the rightmost side of the 5th image is greater than the second projection threshold value.Such as, suppose that horizontal ordinate is from 0, then first calculate vertical projection value corresponding to wj=0, if the vertical projection value that wj=0 is corresponding is less than the second projection threshold value, then calculate vertical projection value corresponding to wj=1, suppose that the vertical projection value that wj=1 is corresponding is greater than the second projection threshold value, then w1=1, on the other hand, first calculate vertical projection value corresponding to wj=w-1, if the vertical projection value that wj=w-1 is corresponding is less than the second projection threshold value, then calculate vertical projection value corresponding to wj=w-2, if the vertical projection value that wj=w-2 is corresponding is also less than the second projection threshold value, then calculate the vertical projection value that wj=w-3 is corresponding again, if the vertical projection value that wj=w-3 is corresponding is greater than the second projection threshold value, then w2=w-3.
Be understandable that, similar ordinate, w1 and w2 is also not limited to be two adjacent horizontal ordinates, such as, can be w1=0, w2=3, and be not limited to w1=0, w2=1.
By the process of this step, the horizontal ordinate pair of each target area can be determined.
S409: export target area.
By above-mentioned process, the ordinate pair of each target area can be determined respectively, and horizontal ordinate pair, according to ordinate to horizontal ordinate to determining target area.
Such as, ordinate is to being <h1, h2>, horizontal ordinate is to being <w1, w2>, then corresponding target area is <h1, h2, w1, the region that w2> is corresponding, concrete, target area is that ordinate is from h1 to h2, and, the region of horizontal ordinate from w1 to w2.
After determining target area, all target areas can be identified on the first image; Or, optimum target region can also be determined in all target areas, the first image identifies optimum target region; Or, different identification means can also be adopted on the first image, identify all target areas, and, identify optimum target region, such as, identify all target areas by white box, identify optimum target region with blue frame.
In the present embodiment, by determining the target area in flow diagram picture, and identify target area in flow diagram picture, directly can orient target area, the automatic identification in realize target region, does not need the manual select target region of user, thus reduces cost and the cost of user operation.The present embodiment is accomplished in several ways the mark of target area, can realize variation.
Fig. 5 is the structural representation of the exhibiting device of the flow diagram picture that another embodiment of the present invention proposes, and this device 50 comprises acquisition module 51, determination module 52 and identification module 53.
Acquisition module 51, for obtaining flow diagram picture;
Such as, user can take pictures to the operation that will search for, and obtains flow diagram picture, or user also directly can select flow diagram picture from existing picture library.
After user takes pictures or selects to obtain flow diagram picture, mobile applications can receive user and takes pictures or select the flow diagram picture that obtains.
Determination module 52, for determining the target area in described flow diagram picture;
Wherein, target area is the region at the content place that user will search for, such as, and the region at exercise question place in flow diagram picture.
Target area can be one or more, multiplely refers at least two.
Optionally, see Fig. 6, described determination module 52 comprises:
First module 521, for extracting the character features information in described flow diagram picture, obtains the image removing non-legible information;
The mode extracting character features information can have multiple, such as, directly can carry out content recognition to original flow diagram picture, thus extract character features information, and character features information is retained in flow diagram picture, remove non-legible information, thus obtain the image removing non-legible information.Concrete, when extracting character features information, first can carry out connected domain division to original flow diagram picture, connected domain divides when such as the number of continuous image vegetarian refreshments identical for pixel value being greater than a threshold value and obtains a connected domain, after connected domain divides, content in each connected domain is identified, connected domain is distinguished character area and non-legible region, character area such as comprises word, letter, one in numeral or multinomial, concrete, can according to picture element density, region picture element density being greater than threshold value is defined as character area.Or,
Optionally, described first module 521 specifically for:
Gray processing is carried out to described flow diagram picture, obtains gray level image;
Described gray level image is sampled, obtains the image after sampling;
By the Nonlinear magnify after described sampling to described flow diagram as formed objects, the image after being amplified;
Calculate the error image of the image after described flow diagram picture and described amplification;
Binary conversion treatment is carried out to described error image, obtains the image after binary conversion treatment;
Remove the connected domain in non-legible region in the image after described binary conversion treatment, obtain the image removing non-legible information.
Above-mentioned particular content see embodiment of the method, can not repeat them here.
Second unit 522, for carrying out horizontal direction projection to the image of the non-legible information of described removal, obtains the ordinate pair of target area;
Optionally, described second unit 522 specifically for:
Obtain h1 and h2, and form ordinate pair by h1 and h2, wherein, as h1≤hi≤h2, the horizontal direction projection value that hi is corresponding is greater than the first projection threshold value, and h1<h2, h1 and h2 represent two ordinates respectively.
First projection threshold value can be determined according to pixel average, such as, the coefficient * pixel average of the first projection threshold value=default, the expression formula of pixel average can specifically: the high h of row removing the sum of non-zero pixel number in the image of non-legible information/the remove image of non-legible information.
Such as, suppose that ordinate is from 0, first can judge whether the horizontal projection value that hi=0 is corresponding is greater than the first projection threshold value, if be greater than, then continue to judge whether the horizontal projection value that hi=1 is corresponding is greater than the first projection threshold value, if be greater than the judgement continuing next adjacent ordinate, suppose that the horizontal projection value up to hi=5 is corresponding is all greater than the first projection threshold value, and horizontal projection value corresponding to hi=6 is less than the first projection threshold value, then one group of ordinate is to being expressed as <0,5>; Afterwards, determined level projection value from hi=7 can be continued and whether be greater than the first projection value.Wherein, the horizontal projection value that hi is corresponding refers to that in the image of the non-legible information of described removal, ordinate is that in the one-row pixels point of hi instruction, pixel value is the number of non-zero pixel.
Be understandable that, ordinate is to being many groups, and many group ordinates can form ordinate queue, and such as, ordinate is to comprising: <0,5>, <7,10> etc.
Further, adopt the ordinate determined of aforesaid way to being many groups, such as, <0,5>, <7,10> etc., afterwards can to many group ordinates to merging and/or Transformatin.
Optionally, see Fig. 6, described acquisition module 52 also comprises:
5th unit 525, for the ordinate of described at least two groups to carrying out Transformatin, and/or merging treatment, obtains the ordinate pair after processing, so that the ordinate after corresponding described process is to determining horizontal ordinate pair.
Optionally, described 5th unit 525 for the ordinate of described at least two groups to carrying out Transformatin, comprising:
Corresponding current ordinate pair to be processed, calculates the difference of current ordinate centering two ordinates;
If described difference is less than the first distance difference, then remove described current ordinate pair.
Such as, to can often organize ordinate to being defined as current ordinate pair successively, suppose that current ordinate is to being <0,5>, then can calculate 5-0, if difference 5-0=5 is less than the first distance difference, then remove this ordinate to <0,5>, otherwise retain, the first distance difference can be default.
Optionally, described 5th unit 525 for the ordinate of described at least two groups to carrying out merging treatment, comprising:
Corresponding first group of adjacent ordinate to be processed to second group of ordinate pair, calculate described first group of ordinate pair spacing value right with described second group of ordinate;
If described spacing value is less than second distance difference, then merge described first group of ordinate to second group of ordinate pair.
Such as, can successively by two groups of adjacent ordinates to be defined as first group of ordinate to second group of ordinate pair, suppose first group of ordinate to second group of ordinate to being <0 respectively, 5> and <7, 10>, the right spacing value of two groups of ordinates refers to the difference of next group ordinate to medium and small coordinate figure and the large coordinate figure of upper one group of ordinate centering, such as, the right spacing value of above-mentioned two groups of ordinates is 7-5=2, if spacing value 2 is less than second distance difference, then merge these two groups of ordinates to <0, 5> and <7, 10>, otherwise nonjoinder, second distance difference can be determined by the coordinate figure right according to two groups of ordinates, such as, suppose that two groups of ordinates are to being <h1 respectively, h2> and <h3, h4>, then second distance difference can be expressed as: (h3-h2)/((h2-h1+h4-h3)/2).
3rd unit 523, for carrying out vertical direction projection to the image of the non-legible information of described removal, corresponding described ordinate is to obtaining horizontal ordinate pair;
Optionally, described 3rd unit 523 specifically for:
Obtain w1 and w2, and form horizontal ordinate pair by w1 and w2, wherein, w1<w2, w1 is the abscissa value that the vertical direction projection value of first correspondence from the leftmost side of the image of the non-legible information of described removal is greater than the second projection threshold value, and w2 is the abscissa value that the vertical direction projection value of first correspondence from the rightmost side of the image of the non-legible information of described removal is greater than the second projection threshold value.
Such as, suppose that horizontal ordinate is from 0, first can judge whether the vertical projection value that wj=0 is corresponding is greater than the second projection threshold value, if be less than, then continue to judge whether the vertical projection value that wj=1 is corresponding is less than the second projection threshold value, if be less than the judgement continuing next adjacent horizontal ordinate, suppose that the horizontal projection value up to wj=5 is corresponding is all less than the second projection threshold value, and vertical projection value corresponding to wj=6 is greater than the second projection threshold value, then w1=6, on the other hand, first judge whether the vertical projection value that wj=w-1 (w is total number of the pixels across point of flow diagram picture) is corresponding is greater than the second projection threshold value, if be less than, then continue to judge whether the vertical projection value that wj=w-2 is corresponding is less than the second projection threshold value, if be less than the judgement continuing next adjacent horizontal ordinate, suppose that the horizontal projection value up to wj=w-8 is corresponding is all less than the second projection threshold value, and vertical projection value corresponding to wj=w-9 is greater than the second projection threshold value, then w2=w-9, therefore, one group of horizontal ordinate is to being expressed as <6, w-9>.Wherein, correspondence often organizes ordinate pair, and the vertical projection value that wj is corresponding refers to that this group ordinate is in the region at place, and in a row pixel of wj instruction, pixel value is the number of non-zero pixel.
Be understandable that, if ordinate is to being many groups, and to many group ordinates to when having carried out removal and/or merging treatment, horizontal ordinate to be corresponding remove and/or ordinate after merging treatment to obtaining.
4th unit 524, for according to described ordinate to described horizontal ordinate pair, obtain the target area in described flow diagram picture.
Such as, corresponding <h1, the horizontal ordinate of h2> is to being <w1, w2>, then target area is <h1, h2, w1, w2>, specifically to refer to as in industry image ordinate from h1 to h2, and the region of the pixel composition of horizontal ordinate from w1 to w2.
Identification module 53, in described flow diagram picture, identifies described target area.
Concrete, in described flow diagram picture, the border of described target area can be shown with crop box form.
Optionally, after on border crop box being arranged on target area, user can also operate crop box further, such as, and the position of mobile crop box, and/or, change the size etc. of crop box.
Optionally, when described target area is at least two, described identification module 53, for identifying described target area, comprising:
Identify all target areas; Or,
In all target areas, determine optimum target region, identify described optimum target region; Or,
Adopt different identification means, identify all target areas, and, identify the optimum target region determined from described all target areas.
Such as, see Fig. 3, on flow diagram picture, can identify all target areas with the first crop box 31, identifying optimum target region with the second crop box 32 is example, and wherein, the first crop box is such as white, and the second crop box is such as blue.
Optionally, described identification module is used for determining optimum target region in all target areas, comprising:
According at least one item in the following item in described target area, in all target areas, determine optimum target region: the content body in target area, the height of target area, the position of target area.
Concrete, content body, highly, the specific requirement that position meets can pre-set.
In another embodiment, see Fig. 6, described target area is one or more, and this device 50 also comprises processing module 54, for obtaining and showing the result for retrieval corresponding with each target area.
After the result for retrieval of multiple target areas that client obtains, the form of different result for retrieval according to page turning can be shown, wherein, the result for retrieval in different target region can the exercise question order corresponding according to target area sort, or, sort according to priority, priority can according to the height of target area, and the information such as position are determined.
In the present embodiment, by determining the target area in flow diagram picture, and identify target area in flow diagram picture, directly can orient target area, the automatic identification in realize target region, does not need the manual select target region of user, thus reduces cost and the cost of user operation.The present embodiment is accomplished in several ways the mark of target area, can realize variation.
It should be noted that, in describing the invention, term " first ", " second " etc. only for describing object, and can not be interpreted as instruction or hint relative importance.In addition, in describing the invention, except as otherwise noted, the implication of " multiple " is two or more.
Describe and can be understood in process flow diagram or in this any process otherwise described or method, represent and comprise one or more for realizing the module of the code of the executable instruction of the step of specific logical function or process, fragment or part, and the scope of the preferred embodiment of the present invention comprises other realization, wherein can not according to order that is shown or that discuss, comprise according to involved function by the mode while of basic or by contrary order, carry out n-back test, this should understand by embodiments of the invention person of ordinary skill in the field.
Should be appreciated that each several part of the present invention can realize with hardware, software, firmware or their combination.In the above-described embodiment, multiple step or method can with to store in memory and the software performed by suitable instruction execution system or firmware realize.Such as, if realized with hardware, the same in another embodiment, can realize by any one in following technology well known in the art or their combination: the discrete logic with the logic gates for realizing logic function to data-signal, there is the special IC of suitable combinational logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA) etc.
Those skilled in the art are appreciated that realizing all or part of step that above-described embodiment method carries is that the hardware that can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, this program perform time, step comprising embodiment of the method one or a combination set of.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, also can be that the independent physics of unit exists, also can be integrated in a module by two or more unit.Above-mentioned integrated module both can adopt the form of hardware to realize, and the form of software function module also can be adopted to realize.If described integrated module using the form of software function module realize and as independently production marketing or use time, also can be stored in a computer read/write memory medium.
The above-mentioned storage medium mentioned can be ROM (read-only memory), disk or CD etc.
In the description of this instructions, specific features, structure, material or feature that the description of reference term " embodiment ", " some embodiments ", " example ", " concrete example " or " some examples " etc. means to describe in conjunction with this embodiment or example are contained at least one embodiment of the present invention or example.In this manual, identical embodiment or example are not necessarily referred to the schematic representation of above-mentioned term.And the specific features of description, structure, material or feature can combine in an appropriate manner in any one or more embodiment or example.
Although illustrate and describe embodiments of the invention above, be understandable that, above-described embodiment is exemplary, can not be interpreted as limitation of the present invention, and those of ordinary skill in the art can change above-described embodiment within the scope of the invention, revises, replace and modification.
Claims (22)
1. a methods of exhibiting for flow diagram picture, is characterized in that, comprising:
Obtain flow diagram picture;
Determine the target area in described flow diagram picture;
In described flow diagram picture, identify described target area.
2. method according to claim 1, is characterized in that, the described target area determined in described flow diagram picture, comprising:
Extract the character features information in described flow diagram picture, obtain the image removing non-legible information;
Horizontal direction projection is carried out to the image of the non-legible information of described removal, obtains the ordinate pair of target area;
Carry out vertical direction projection to the image of the non-legible information of described removal, corresponding described ordinate is to obtaining horizontal ordinate pair;
According to described ordinate to described horizontal ordinate pair, obtain the target area in described flow diagram picture.
3. method according to claim 2, is characterized in that, the character features information in the described flow diagram picture of described extraction, obtains the image removing non-legible information, comprising:
Gray processing is carried out to described flow diagram picture, obtains gray level image;
Described gray level image is sampled, obtains the image after sampling;
By the Nonlinear magnify after described sampling to described flow diagram as formed objects, the image after being amplified;
Calculate the error image of the image after described flow diagram picture and described amplification;
Binary conversion treatment is carried out to described error image, obtains the image after binary conversion treatment;
Remove the connected domain in non-legible region in the image after described binary conversion treatment, obtain the image of the non-legible information of described removal.
4. method according to claim 2, is characterized in that, the described image to the non-legible information of described removal carries out horizontal direction projection, obtains the ordinate pair of target area, comprising:
Obtain h1 and h2, and form ordinate pair by h1 and h2, wherein, as h1≤hi≤h2, the horizontal direction projection value that hi is corresponding is greater than the first projection threshold value, and h1<h2, h1 and h2 represent two ordinates respectively.
5. method according to claim 4, is characterized in that, when described ordinate is to when being at least two groups, described method also comprises:
To the ordinate of described at least two groups to carrying out Transformatin, and/or merging treatment, obtains the ordinate pair after processing, so that the ordinate after corresponding described process is to determining horizontal ordinate pair.
6. method according to claim 5, is characterized in that, the described ordinate to described at least two groups, to carrying out Transformatin, comprising:
Corresponding current ordinate pair to be processed, calculates the difference of current ordinate centering two ordinates;
If described difference is less than the first distance difference, then remove described current ordinate pair.
7. method according to claim 5, is characterized in that, the described ordinate to described at least two groups, to carrying out merging treatment, comprising:
Corresponding first group of adjacent ordinate to be processed to second group of ordinate pair, calculate described first group of ordinate pair spacing value right with described second group of ordinate;
If described spacing value is less than second distance difference, then merge described first group of ordinate to second group of ordinate pair.
8. method according to claim 2, is characterized in that, the described image to the non-legible information of described removal carries out vertical direction projection, and corresponding described ordinate, to obtaining horizontal ordinate pair, comprising:
Obtain w1 and w2, and form horizontal ordinate pair by w1 and w2, wherein, w1<w2, w1 is the abscissa value that the vertical direction projection value of first correspondence from the leftmost side of the image of the non-legible information of described removal is greater than the second projection threshold value, and w2 is the abscissa value that the vertical direction projection value of first correspondence from the rightmost side of the image of the non-legible information of described removal is greater than the second projection threshold value.
9. the method according to any one of claim 1-8, is characterized in that, when described target area is at least two, described in identify described target area, comprising:
Identify all target areas; Or,
In all target areas, determine optimum target region, identify described optimum target region; Or,
Adopt different identification means, identify all target areas, and, identify the optimum target region determined from described all target areas.
10. method according to claim 9, is characterized in that, describedly in all target areas, determines optimum target region, comprising:
According at least one item in the following item in described target area, in all target areas, determine optimum target region: the content body in target area, the height of target area, the position of target area.
11. methods according to claim 1, it is characterized in that, described target area is one or more, described method also comprises:
Obtain and show the result for retrieval corresponding with each target area.
The exhibiting device of 12. 1 kinds of flow diagram pictures, is characterized in that, comprising:
Acquisition module, for obtaining flow diagram picture;
Determination module, for determining the target area in described flow diagram picture;
Identification module, in described flow diagram picture, identifies described target area.
13. devices according to claim 12, is characterized in that, described determination module comprises:
First module, for extracting the character features information in described flow diagram picture, obtains the image removing non-legible information;
Second unit, for carrying out horizontal direction projection to the image of the non-legible information of described removal, obtains the ordinate pair of target area;
Unit the 3rd, for carrying out vertical direction projection to the image of the non-legible information of described removal, corresponding described ordinate is to obtaining horizontal ordinate pair;
Unit the 4th, for according to described ordinate to described horizontal ordinate pair, obtain the target area in described flow diagram picture.
14. devices according to claim 13, is characterized in that, described first module specifically for:
Gray processing is carried out to described flow diagram picture, obtains gray level image;
Described gray level image is sampled, obtains the image after sampling;
By the Nonlinear magnify after described sampling to described flow diagram as formed objects, the image after being amplified;
Calculate the error image of the image after described flow diagram picture and described amplification;
Binary conversion treatment is carried out to described error image, obtains the image after binary conversion treatment;
Remove the connected domain in non-legible region in the image after described binary conversion treatment, obtain the image of the non-legible information of described removal.
15. devices according to claim 13, is characterized in that, described second unit specifically for:
Obtain h1 and h2, and form ordinate pair by h1 and h2, wherein, as h1≤hi≤h2, the horizontal direction projection value that hi is corresponding is greater than the first projection threshold value, and h1<h2, h1 and h2 represent two ordinates respectively.
16. devices according to claim 15, is characterized in that, described acquisition module also comprises:
Unit the 5th, for the ordinate of described at least two groups to carrying out Transformatin, and/or merging treatment, obtains the ordinate pair after processing, so that the ordinate after corresponding described process is to determining horizontal ordinate pair.
17. devices according to claim 16, is characterized in that, described Unit the 5th to be used for the ordinate of described at least two groups, to carrying out Transformatin, comprising:
Corresponding current ordinate pair to be processed, calculates the difference of current ordinate centering two ordinates;
If described difference is less than the first distance difference, then remove described current ordinate pair.
18. devices according to claim 16, is characterized in that, described Unit the 5th to be used for the ordinate of described at least two groups, to carrying out merging treatment, comprising:
Corresponding first group of adjacent ordinate to be processed to second group of ordinate pair, calculate described first group of ordinate pair spacing value right with described second group of ordinate;
If described spacing value is less than second distance difference, then merge described first group of ordinate to second group of ordinate pair.
19. devices according to claim 13, is characterized in that, described Unit the 3rd specifically for:
Obtain w1 and w2, and form horizontal ordinate pair by w1 and w2, wherein, w1<w2, w1 is the abscissa value that the vertical direction projection value of first correspondence from the leftmost side of the image of the non-legible information of described removal is greater than the second projection threshold value, and w2 is the abscissa value that the vertical direction projection value of first correspondence from the rightmost side of the image of the non-legible information of described removal is greater than the second projection threshold value.
20. devices according to any one of claim 12-19, it is characterized in that, when described target area is at least two, described identification module is used for identifying described target area, comprising:
Identify all target areas; Or,
In all target areas, determine optimum target region, identify described optimum target region; Or,
Adopt different identification means, identify all target areas, and, identify the optimum target region determined from described all target areas.
21. devices according to claim 20, is characterized in that, described identification module is used for determining optimum target region in all target areas, comprising:
According at least one item in the following item in described target area, in all target areas, determine optimum target region: the content body in target area, the height of target area, the position of target area.
22. devices according to claim 12, it is characterized in that, described target area is one or more, described device also comprises:
Processing module, for obtaining and showing the result for retrieval corresponding with each target area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510047554.1A CN104573675B (en) | 2015-01-29 | 2015-01-29 | The methods of exhibiting and device of operation image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510047554.1A CN104573675B (en) | 2015-01-29 | 2015-01-29 | The methods of exhibiting and device of operation image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104573675A true CN104573675A (en) | 2015-04-29 |
| CN104573675B CN104573675B (en) | 2018-10-09 |
Family
ID=53089697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510047554.1A Active CN104573675B (en) | 2015-01-29 | 2015-01-29 | The methods of exhibiting and device of operation image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104573675B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389165A (en) * | 2015-10-21 | 2016-03-09 | 广州视睿电子科技有限公司 | Document picture display method and apparatus, and terminal |
| CN106250518A (en) * | 2016-08-03 | 2016-12-21 | 广东小天才科技有限公司 | Intelligence searches topic method and device |
| CN106293036A (en) * | 2015-06-12 | 2017-01-04 | 联想(北京)有限公司 | A kind of exchange method and electronic equipment |
| CN107016392A (en) * | 2016-01-27 | 2017-08-04 | 四川效率源信息安全技术股份有限公司 | A kind of method of text border in removal picture |
| CN108021320A (en) * | 2017-12-25 | 2018-05-11 | 广东小天才科技有限公司 | A kind of electronic equipment topic searching method and electronic equipment |
| CN108304360A (en) * | 2017-12-19 | 2018-07-20 | 深圳市因尚网络科技股份有限公司 | Competition for orders control method, equipment and computer readable storage medium |
| CN111104883A (en) * | 2019-12-09 | 2020-05-05 | 平安国际智慧城市科技股份有限公司 | Job answer extraction method, device, equipment and computer readable storage medium |
| CN112488890A (en) * | 2021-02-05 | 2021-03-12 | 南京熊大未来窗智能科技有限公司 | Interactive learning auxiliary method based on remote display |
| CN113505745A (en) * | 2021-07-27 | 2021-10-15 | 京东科技控股股份有限公司 | Character recognition method and device, electronic equipment and storage medium |
| CN113537225A (en) * | 2020-04-22 | 2021-10-22 | 华晨宝马汽车有限公司 | Method, electronic device, and storage medium for character recognition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110222773A1 (en) * | 2010-03-10 | 2011-09-15 | Microsoft Corporation | Paragraph recognition in an optical character recognition (ocr) process |
| CN103268481A (en) * | 2013-05-29 | 2013-08-28 | 焦点科技股份有限公司 | Method for extracting text in complex background image |
| CN103456195A (en) * | 2012-05-28 | 2013-12-18 | 上海易酷信息技术服务有限公司 | Smart phone based remote question answering and tutoring system and using method thereof |
| CN103544475A (en) * | 2013-09-23 | 2014-01-29 | 方正国际软件有限公司 | Method and system for recognizing layout types |
-
2015
- 2015-01-29 CN CN201510047554.1A patent/CN104573675B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110222773A1 (en) * | 2010-03-10 | 2011-09-15 | Microsoft Corporation | Paragraph recognition in an optical character recognition (ocr) process |
| CN103456195A (en) * | 2012-05-28 | 2013-12-18 | 上海易酷信息技术服务有限公司 | Smart phone based remote question answering and tutoring system and using method thereof |
| CN103268481A (en) * | 2013-05-29 | 2013-08-28 | 焦点科技股份有限公司 | Method for extracting text in complex background image |
| CN103544475A (en) * | 2013-09-23 | 2014-01-29 | 方正国际软件有限公司 | Method and system for recognizing layout types |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106293036A (en) * | 2015-06-12 | 2017-01-04 | 联想(北京)有限公司 | A kind of exchange method and electronic equipment |
| CN106293036B (en) * | 2015-06-12 | 2021-02-19 | 联想(北京)有限公司 | Interaction method and electronic equipment |
| CN105389165A (en) * | 2015-10-21 | 2016-03-09 | 广州视睿电子科技有限公司 | Document picture display method and apparatus, and terminal |
| CN105389165B (en) * | 2015-10-21 | 2019-04-30 | 广州视睿电子科技有限公司 | A kind of document image display method, device and terminal |
| CN107016392A (en) * | 2016-01-27 | 2017-08-04 | 四川效率源信息安全技术股份有限公司 | A kind of method of text border in removal picture |
| CN106250518A (en) * | 2016-08-03 | 2016-12-21 | 广东小天才科技有限公司 | Intelligence searches topic method and device |
| CN108304360A (en) * | 2017-12-19 | 2018-07-20 | 深圳市因尚网络科技股份有限公司 | Competition for orders control method, equipment and computer readable storage medium |
| CN108021320B (en) * | 2017-12-25 | 2020-07-28 | 广东小天才科技有限公司 | Electronic equipment and item searching method thereof |
| CN108021320A (en) * | 2017-12-25 | 2018-05-11 | 广东小天才科技有限公司 | A kind of electronic equipment topic searching method and electronic equipment |
| CN111104883A (en) * | 2019-12-09 | 2020-05-05 | 平安国际智慧城市科技股份有限公司 | Job answer extraction method, device, equipment and computer readable storage medium |
| CN111104883B (en) * | 2019-12-09 | 2023-06-06 | 平安国际智慧城市科技股份有限公司 | Job answer extraction method, apparatus, device and computer readable storage medium |
| CN113537225A (en) * | 2020-04-22 | 2021-10-22 | 华晨宝马汽车有限公司 | Method, electronic device, and storage medium for character recognition |
| CN112488890A (en) * | 2021-02-05 | 2021-03-12 | 南京熊大未来窗智能科技有限公司 | Interactive learning auxiliary method based on remote display |
| CN112488890B (en) * | 2021-02-05 | 2021-05-07 | 南京熊大未来窗智能科技有限公司 | Interactive learning auxiliary method based on remote display |
| CN113505745A (en) * | 2021-07-27 | 2021-10-15 | 京东科技控股股份有限公司 | Character recognition method and device, electronic equipment and storage medium |
| CN113505745B (en) * | 2021-07-27 | 2024-04-05 | 京东科技控股股份有限公司 | Character recognition method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104573675B (en) | 2018-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104573675A (en) | Operating image displaying method and device | |
| US10896349B2 (en) | Text detection method and apparatus, and storage medium | |
| Diem et al. | cBAD: ICDAR2017 competition on baseline detection | |
| CN107016387B (en) | Method and device for identifying label | |
| CN105868758B (en) | method and device for detecting text area in image and electronic equipment | |
| CN111681273B (en) | Image segmentation method and device, electronic equipment and readable storage medium | |
| CN106940799B (en) | Text image processing method and device | |
| US11521109B2 (en) | Information processing apparatus and method of controlling information processing apparatus | |
| CN110942074A (en) | Character segmentation recognition method and device, electronic equipment and storage medium | |
| CN103793717A (en) | Methods for determining image-subject significance and training image-subject significance determining classifier and systems for same | |
| CN113627411A (en) | Super-resolution-based commodity identification and price matching method and system | |
| JP2021135993A (en) | Text recognition method, text recognition apparatus, electronic device, and storage medium | |
| JPWO2016063483A1 (en) | Vending machine recognition apparatus, product shelf recognition apparatus, vending machine recognition method, program, and image processing apparatus | |
| CN103034833A (en) | Bar code positioning method and bar code detection device | |
| CN110223340B (en) | Method and device for recognizing shelf position of book by robot | |
| CN112200218B (en) | Model training method and device and electronic equipment | |
| CN111797704B (en) | Action recognition method based on related object perception | |
| CN112613367A (en) | Bill information text box acquisition method, system, equipment and storage medium | |
| CN112434585A (en) | Method, system, electronic device and storage medium for identifying virtual reality of lane line | |
| CN111401438B (en) | Image sorting method, device and system | |
| CN108446693B (en) | Marking method, system, equipment and storage medium of target to be identified | |
| CN113361462B (en) | Method and device for video processing and caption detection model | |
| CN113807407B (en) | Target detection model training method, model performance detection method and device | |
| CN114118950A (en) | Method and device for arranging consultation scheme based on project | |
| CN111291756B (en) | Method and device for detecting text region in image, computer equipment and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160216 Address after: 100085, Beijing, Haidian District on the road to entrepreneurship No. 1, 28, 4, room 417 Applicant after: Operation education technology (Beijing) Co., Ltd. Address before: 100085 Beijing, Haidian District, No. ten on the ground floor, No. 10 Baidu building, layer three Applicant before: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |